Writing on small form factor devices such as smartphones is inefficient due to the small dimensions of such devices. This disclosure describes techniques that support natural-language, context-aware voice commands that refer to individual words, sentences, paragraphs, sections, chapters, etc. of text content. Various features are supported, such as: automatically splitting text into paragraphs; creating lists; using different fonts for subheadings, chapter titles, etc.; inserting footnotes; adding citations and references; etc. To assist the user in navigating the document, the transcribed text is displayed overlaid with annotations that indicate available commands; numbered textual components; etc. Machine learning and natural language processing techniques are used to automatically differentiate between text and commands.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.